Nutrients Detection and Adulteration Analysis of Vegetables and Fruits for Pregnant Women Using Machine Learning

Abstract

The accurate detection and analysis of NPK values in fruits and vegetables play a significant role in ensuring their optimal growth and health. The authors propose a system for NPK value detection and analyse fruits and vegetables using NPK sensors and identifying the vegetable and fertilizer recommendation based on NPK values using random forest and SGD algorithms. The proposed system involves inserting NPK sensor into the vegetable, which measures the NPK value, and processing the data using an Arduino board. The NPK values are then read from the serial monitor using Python and used to identify the vegetable using the random forest algorithm. The system also recommends suitable fertilizers based on the NPK values using the SGD algorithm. The system's accuracy is enhanced by using a dataset of NPK values for various vegetables and fruits. The results are displayed in Stream lit, a web application framework. The proposed system enhanced accuracy in NPK value detection and analysis, improved vegetable identification and fertilizer recommendation, leading to improved crop yield and quality.